io.github.Nutshell2000/agent-data-tools-ai

Est-ce que io.github.Nutshell2000/agent-data-tools-ai est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Nutshell2000/agent-data-tools-ai » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 15 outils

• ai_chat≈ 316 tokens

  Send a prompt, get an answer from Llama 3.1 8B Instruct, with an optional system prompt, up to 1,024 output tokens and adjustable temperature. Use for drafting, reasoning steps, Q&A and any quick LLM call without an AI provider account. For harder reasoning use ai_chat_large. Example: prompt=Explain x402 in one sentence.. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (4)

  Paramètres

  • prompt · string · requis
    User prompt, up to 8,000 characters
  • system · string · optionnel
    Optional system prompt, up to 2,000 characters
  • maxTokens · integer · optionnel
    Maximum output tokens, 1-1024 (default 400)
  • temperature · number · optionnel
    0-1.5 (default 0.6)

  Exemple d'appel

  {"name": "ai_chat", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_chat_large≈ 366 tokens

  Send a prompt, get an answer from a larger open model: Llama 3.3 70B Instruct (default) or OpenAI gpt-oss-120b, with an optional system prompt, up to 1,024 output tokens and adjustable temperature. Same call as /ai/chat with a stronger model. Use when the 8B model is not enough: reasoning, drafting and Q&A. Example: prompt=Explain x402 in one sentence.. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (5)

  Paramètres

  • model · string · optionnel · llama-3.3-70b | gpt-oss-120b
    llama-3.3-70b (default) or gpt-oss-120b
  • prompt · string · requis
    User prompt, up to 8,000 characters
  • system · string · optionnel
    Optional system prompt, up to 2,000 characters
  • maxTokens · integer · optionnel
    Maximum output tokens, 1-1024 (default 400)
  • temperature · number · optionnel
    0-1.5 (default 0.6)

  Exemple d'appel

  {"name": "ai_chat_large", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_classify≈ 229 tokens

  Zero-shot classification: give text and 2-20 candidate labels, get the best label, a short reason and a ranking. Use for routing tickets, tagging content, intent detection and moderation queues. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text to classify, up to 8,000 characters
  • labels · string · requis
    Comma-separated candidate labels (2-20)

  Exemple d'appel

  {"name": "ai_classify", "arguments": {"text": "texte", "labels": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_embed≈ 216 tokens

  A 1,024-dimension embedding vector for up to 4,000 characters of text in 100+ languages, from BAAI's BGE-M3. Use for semantic search, RAG retrieval, clustering and deduplication. Example: text=pay-per-call APIs for AI agents. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    Text to embed, up to 4,000 characters

  Exemple d'appel

  {"name": "ai_embed", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_extract_json≈ 234 tokens

  Pull named fields out of unstructured text (emails, invoices, listings, bios) and get them back as a JSON object, with null for anything not present. Use to turn messy text into structured data for an agent. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Source text, up to 12,000 characters
  • fields · string · requis
    Comma-separated field names to extract (1-30)

  Exemple d'appel

  {"name": "ai_extract_json", "arguments": {"text": "texte", "fields": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_keywords≈ 213 tokens

  The most important keywords and key phrases of a text, most relevant first. Use for tagging, SEO, search indexing and topic detection. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text, up to 12,000 characters
  • count · integer · optionnel
    How many, 3-30 (default 10)

  Exemple d'appel

  {"name": "ai_keywords", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_outline≈ 249 tokens

  A structured Markdown outline (headings and bullet points) of a text you send, or a suggested outline for a topic. Use to plan articles, reports, talks and documentation. Example: text=How small businesses can accept stablecoin payments. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text to outline, or a topic, up to 12,000 characters
  • depth · integer · optionnel
    Heading levels, 1-3 (default 2)

  Exemple d'appel

  {"name": "ai_outline", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_rewrite≈ 272 tokens

  Rewrite text to be more formal, casual, simpler, shorter, friendlier, more professional or more persuasive, keeping the meaning and language. Use to polish emails, replies, product copy and messages. Example: text=hey, cant make it tmrw, can we move to thu?. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text, up to 8,000 characters
  • style · string · optionnel · formal | casual | simpler | shorter | friendly | professional | persuasive
    formal, casual, simpler, shorter, friendly, professional or persuasive (default professional)

  Exemple d'appel

  {"name": "ai_rewrite", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_sentiment≈ 217 tokens

  Positive or negative sentiment of English text with a confidence score, from a DistilBERT model fine-tuned on SST-2. Use to triage reviews, support messages, social posts and replies. Example: text=The checkout was fast and support answered within minutes.. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    English text, up to 4,000 characters

  Exemple d'appel

  {"name": "ai_sentiment", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_speech≈ 276 tokens

  Turn up to 1,000 characters of text into natural speech as an audio file (base64, with its content type), in English, Spanish, French, Chinese, Japanese or Korean, with MeloTTS. Use for voice replies, audio notes, accessibility and phone or chat bots. Example: text=Your payment was received. Thank you!. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | es | fr | zh | ja | ko
    Language: en, es, fr, zh, ja or ko (default en)
  • text · string · requis
    Text to speak, up to 1,000 characters

  Exemple d'appel

  {"name": "ai_speech", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_summarize_text≈ 238 tokens

  Summarize up to 12,000 characters of text you send into a few sentences plus bullet key points. Use for long emails, documents, transcripts and tool outputs (for a web page by URL, use /summarize). Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text to summarize, up to 12,000 characters
  • sentences · integer · optionnel
    Summary length in sentences, 1-8 (default 3)

  Exemple d'appel

  {"name": "ai_summarize_text", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_translate≈ 262 tokens

  Translate text between about 100 languages with Meta's M2M100 1.2B model. Give the target language as an ISO code such as en, sv, de, fr, es, zh or ja; the source language is optional. Use to localise messages and documents. Example: text=Payment received, thank you!, to=sv. Price $0.003/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (3)

  Paramètres

  • to · string · requis
    Target language code, e.g. sv
  • from · string · optionnel
    Source language code (default en)
  • text · string · requis
    Text, up to 4,000 characters

  Exemple d'appel

  {"name": "ai_translate", "arguments": {"to": "texte", "text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• describe≈ 267 tokens

  Vision model for an image at a public URL: get a detailed description including any visible text, or pass a question to ask something specific about the image. Accepts PNG, JPEG, WebP and GIF up to 3 MB. Use for alt text, OCR-style reading of screenshots, chart reading and content checks. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of a PNG, JPEG, WebP or GIF image (max 3 MB)
  • question · string · optionnel
    Optional question about the image (max 300 characters); default is a detailed description

  Exemple d'appel

  {"name": "describe", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• image≈ 274 tokens

  Text-to-image generation with FLUX.1 schnell. Send a prompt, get a 1024x1024 JPEG back as base64 in a few seconds. Use for illustrations, thumbnails, mockups, avatars and social media images. Optional steps parameter (1-8, default 4) trades speed for detail. Example: prompt=a lighthouse on a cliff at sunset, watercolor. Price $0.02/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (2)

  Paramètres

  • steps · integer · optionnel
    Diffusion steps, 1-8 (default 4)
  • prompt · string · requis
    What the image should show (3-800 characters)

  Exemple d'appel

  {"name": "image", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• transcribe≈ 260 tokens

  Transcribe speech from an audio file at a public URL using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count. Accepts common formats such as MP3, WAV, M4A and OGG up to 5 MB. Use for voice notes, podcast clips, meeting snippets and voice messages. Example: url=https://commons.wikimedia.org/wiki/Special:FilePath/En-us-hello.ogg. Price $0.02/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of an audio file (max 5 MB)

  Exemple d'appel

  {"name": "transcribe", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://agent-data-tools.revmesh2074.workers.dev/mcp/ai